Jevto — Development skill for Claude Code
Command-output selection for coding agents, with exact local recall and optional Jev ranking.
How to install Jevto
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open mattbaconz/jevto and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Jevto does
Command-output selection for coding agents, with exact local recall and optional Jev ranking.
Alternatives in Development
- Code Review Graph — Local knowledge graph for Claude Code 3.7k ★
- Coding Agent Session Search — Unified TUI and CLI to index and search your local coding agent session history across 11+ providers (Codex, C 708 ★
- Kuato — Built for Claude Code but works in any agent that supports skills, easily recall what you discussed with your 176 ★
README
why agent read 173 line when 15 line say same thing?
Agent run `cargo test`. Terminal throw 173 line at agent. 150 line say `ok`. Agent pay for all 173. Agent need maybe 5.
**JevTO stand between command and agent.** Keep fail. Keep assert. Keep line goal ask about. Rest go in **cave**. Cave not trash: cave keep every byte, and `jevto recall` bring any of it back exact. No rerun. No paraphrase. No guess.
**Status:** experimental (v0.1.1). Apache-2.0. Not made by TypeSafe AI or RTK.
[Website](https://jevto.xyz/) · [Install and docs](https://jevto.xyz/docs/) · [Recorded demo](https://jevto.xyz/demo/) · [Releases](https://github.com/mattbaconz/jevto/releases) · [Support on Ko-fi](https://ko-fi.com/mattbaconz)
🪨 Before, after
**Before.** Native `cargo test`: 173 lines, ~1,245 tokens.
running 151 tests
test tests::case_000 ... ok
test tests::case_001 ... ok
test tests::case_002 ... ok
... 147 more ok lines ...
test tRelated Skills
Leash
Jev-powered guardrail that keeps a coding agent's output quality on a short leash: judges every turn against y
Astra Jev Harness
Agent Skills for Codex Desktop and Claude Code, plus a Codex CLI harness. Jev-assisted context selection. / Co
Skillmem
Self-improving skill memory for coding agents: learn, recall, reinforce, decay — with provenance on every memo
Omnirecall
🔎 Recall past coding conversations across Pi, Codex, and Claude Code from one searchable local archive.
Local Tts
Make your coding agent talk to you! -- Simple, offline and online (optional). Ask your coding agent to install
Agent Ledger
A local workspace to understand coding-agent usage, recover past decisions, and keep useful project context. P
Related Agents
Handoff Writer
Produces run-local handoff artifacts and optional publishable handoff output for a new session.
Jev Judge
Reusable Judge/Verifier question-drafter for text-shaped deliverables — pass/fail, meets-bar yes/no, or rubric
Memory Recall
Use this agent PROACTIVELY before starting complex, multi-step implementations or when encountering unfamiliar
